{"id":"W3007638626","doi":"10.2196/16153","title":"Explanatory Model of Dry Eye Disease Using Health and Nutrition Examinations: Machine Learning and Network-Based Factor Analysis From a National Survey","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Ocular Surface and Contact Lens","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Logistic regression; National Health and Nutrition Examination Survey; Medicine; Centrality; Lasso (programming language); Receiver operating characteristic; Machine learning; Artificial intelligence; Ranking (information retrieval); Explanatory model; Computer science; Statistics; Environmental health; Mathematics; Population","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000302235,0.0001028243,0.0003474918,0.0001066625,0.00007012534,0.00001480535,0.00003835986,0.00007964675,0.00005377764],"category_scores_gemma":[0.0004162055,0.00009208103,0.0000554854,0.0002939116,0.0000618903,0.0001310221,0.00003318548,0.0002374387,8.323121e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004016814,"about_ca_system_score_gemma":0.0004731976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007998874,"about_ca_topic_score_gemma":0.00003842092,"domain_scores_codex":[0.9985797,0.00009266407,0.0004498463,0.00009068947,0.0006553316,0.0001317257],"domain_scores_gemma":[0.9988397,0.0001838844,0.000189877,0.00006597794,0.0001223537,0.0005981623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001632565,0.00009974658,0.9946187,0.000559539,0.0002067567,0.000002716617,0.00152746,0.00154229,0.00001119349,0.00004468629,0.00001925145,0.001204377],"study_design_scores_gemma":[0.001096503,0.00008936873,0.08826858,0.0001589804,0.0001029688,4.186644e-8,0.0003003935,0.9097816,0.000004516861,0.00002752843,0.00009668935,0.00007277276],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9614195,0.001068069,0.03643498,0.0005178504,0.00001048923,0.000244132,0.0002607327,0.00002672055,0.00001753675],"genre_scores_gemma":[0.9919048,0.0002930131,0.004124452,0.002470719,0.00004041164,0.000008378628,0.001147297,0.000007520119,0.000003416377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9082394,"threshold_uncertainty_score":0.3754956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0504425103468915,"score_gpt":0.3288690098796588,"score_spread":0.2784264995327673,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}